US 11,853,703 B2
Processing transactional feedback
Don Kumudu Janaka Ranatunga, Cupertino, CA (US); Marie Michelle Rhea Foster, San Jose, CA (US); Brandon An Lai, Morgan Hill, CA (US); Sanjika Hewavitharana, Milpitas, CA (US); Jason Diran, San Jose, CA (US); and Canran Xu, San Jose, CA (US)
Assigned to EBAY INC., San Jose, CA (US)
Filed by eBay Inc., San Jose, CA (US)
Filed on Mar. 9, 2021, as Appl. No. 17/195,888.
Application 17/195,888 is a continuation of application No. 16/461,125, granted, now 10,990,764, previously published as PCT/CN2018/087485, filed on May 18, 2018.
Prior Publication US 2021/0192145 A1, Jun. 24, 2021
Int. Cl. G06F 40/30 (2020.01); G06N 20/00 (2019.01); H04L 51/212 (2022.01)
CPC G06F 40/30 (2020.01) [G06N 20/00 (2019.01); H04L 51/212 (2022.05)] 20 Claims
OG exemplary drawing
 
1. A computer implemented method comprising:
receiving one or more comments associated with a transaction by a user;
classifying, by at least one processor, at least one of the one or more comments into a sentiment classification;
selecting, by the at least one processor, a first predefined category from a plurality of predefined categories for the one or more comments based at least in part on one or more terms in the one or more comments and the sentiment classification;
generating, by the at least one processor, a sub-category of the first predefined category based at least in part on applying a natural language processing model to the one or more comments to identify a feedback topic associated with the one or more comments:
identifying, by the at least one processor, trend data associated with the sub-category of the first predefined category based at least in part on the one or more comments and the sentiment classification; and
transmitting the identified trend data associated with the sub-category of the first predefined category to a client device.